© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71131
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to theoretical physics and particle interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abus
    -0.06
    TL
    -0.06
    abin
    -0.06
    antee
    -0.06
    duit
    -0.06
     ges
    -0.05
    ress
    -0.05
    ious
    -0.05
     TL
    -0.05
     Snapdragon
    -0.05
    POSITIVE LOGITS
    æŁ´
    0.07
     Puzzle
    0.07
    ordion
    0.06
     puzzle
    0.06
    indr
    0.06
    ottes
    0.06
     regulators
    0.06
    озем
    0.06
     chrom
    0.06
    Balance
    0.06
    Activations Density 0.021%

    No Known Activations